Upload 2 files

data/sample_sentences.txt

@@ -0,0 +1,8 @@
+Artificial intelligence is transforming the world.
+Cats are amazing pets.
+The capital of France is Paris.
+The Eiffel Tower is in France.
+Deep learning enables image recognition.
+Dogs are loyal companions.
+The sun rises in the east.
+The moon orbits the Earth.

src/visualizer.py

@@ -0,0 +1,41 @@
+import torch
+from sentence_transformers import SentenceTransformer
+import matplotlib.pyplot as plt
+from sklearn.decomposition import PCA
+from sklearn.manifold import TSNE
+
+# Detect device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+print(f"Using device: {device}")
+
+# Load dataset
+with open("../data/sample_sentences.txt", "r", encoding="utf-8") as f:
+    sentences = [line.strip() for line in f if line.strip()]
+
+# Load embedding model
+model = SentenceTransformer('all-MiniLM-L6-v2', device=device)
+
+# Create embeddings
+embeddings = model.encode(sentences)
+
+# PCA Visualization
+pca = PCA(n_components=2)
+pca_result = pca.fit_transform(embeddings)
+
+plt.figure(figsize=(8,6))
+plt.scatter(pca_result[:,0], pca_result[:,1])
+for i, txt in enumerate(sentences):
+    plt.annotate(txt, (pca_result[i,0], pca_result[i,1]))
+plt.title("Text Embeddings (PCA)")
+plt.show()
+
+# t-SNE Visualization
+tsne = TSNE(n_components=2, random_state=42, perplexity=5)
+tsne_result = tsne.fit_transform(embeddings)
+
+plt.figure(figsize=(8,6))
+plt.scatter(tsne_result[:,0], tsne_result[:,1])
+for i, txt in enumerate(sentences):
+    plt.annotate(txt, (tsne_result[i,0], tsne_result[i,1]))
+plt.title("Text Embeddings (t-SNE)")
+plt.show()